Image processing device, image processing method, program, and recording medium

Abstract

Provided are an image processing device, an image processing method, a program, and a recording medium for appropriately evaluating blurring of an image according to a background in the image. The image processing device of an embodiment of the present invention includes a processor, and the processor acquires an image, specifies a subject region in which a selected subject is captured and a background region except for the subject region, in the image, calculates a difference between a degree of blurring in the subject region and a degree of blurring in the background region, acquires information as to whether or not an imaging location of the image is outdoors, and calculates an evaluation value regarding blurring of the image on the basis of the difference and the information.

What is claimed is: 
     
         1 . An image processing device comprising:
 a processor,   wherein the processor
 acquires an image, 
 specifies a subject region in which a main subject is captured and a background region except for the subject region, in the image, 
 calculates a difference between a degree of blurring in the subject region and a degree of blurring in the background region, 
 acquires information as to whether or not an imaging location of the image is outdoors, and 
 calculates an evaluation value regarding blurring of the image on the basis of the difference and the information. 
   
     
     
         2 . The image processing device according to  claim 1 ,
 wherein the processor calculates the evaluation value such that the evaluation value increases as an absolute value of the difference increases.   
     
     
         3 . The image processing device according to  claim 1 ,
 wherein the processor calculates the evaluation value such that the evaluation value increases as a probability of the imaging location being outdoors increases.   
     
     
         4 . The image processing device according to  claim 1 ,
 wherein the processor calculates the evaluation value such that the evaluation value decreases as the degree of blurring in the subject region increases.   
     
     
         5 . The image processing device according to  claim 1 ,
 wherein the processor
 acquires a numerical value defined within a range of 0 to 1, as the information, and 
   the numerical value increases as a probability of the imaging location being outdoors increases.   
     
     
         6 . The image processing device according to  claim 5 ,
 wherein the processor acquires the numerical value for the image by using a numerical value output model that outputs the numerical value for an input image, and   the numerical value output model is constructed through machine learning using training data including an image and the numerical value.   
     
     
         7 . The image processing device according to  claim 5 ,
 wherein the processor acquires the image to which ancillary information indicating a position of the imaging location is added, and   the processor acquires the numerical value corresponding to the ancillary information.   
     
     
         8 . The image processing device according to  claim 1 ,
 wherein the processor sets a subject of which a face is detected, a subject detected by a subject detection model that detects a subject in an input image, a subject designated by a user, or a subject closest to a reference position in the image, as the main subject, and specifies a region in which the main subject is captured, as the subject region.   
     
     
         9 . The image processing device according to  claim 1 ,
 wherein the processor calculates a score defined within a range of 0 to 1 as the degree of blurring in each of the subject region and the background region, and calculates the difference from the score for the subject region and the score for the background region.   
     
     
         10 . The image processing device according to  claim 9 ,
 wherein the processor
 divides the image into a plurality of regions, 
 calculates the score for the subject region by calculating the score for a region corresponding to the subject region, among the plurality of regions, for each region and averaging the scores calculated for respective regions, 
 calculates the score for the background region by calculating the score for a region corresponding to the background region, among the plurality of regions, for each region and averaging the scores calculated for respective regions, and 
 calculates the difference by subtracting one from the other of the score for the subject region and the score for the background region. 
   
     
     
         11 . An image processing method executed by a processor, the method comprising:
 a step of, by the processor, acquiring an image;   a step of, by the processor, specifying a subject region in which a main subject is captured and a background region except for the subject region, in the image;   a step of, by the processor, calculating a difference between a degree of blurring in the subject region and a degree of blurring in the background region;   a step of, by the processor, acquiring information as to whether or not an imaging location of the image is outdoors; and   a step of, by the processor, calculating an evaluation value regarding blurring of the image on the basis of the difference and the information.   
     
     
         12 . The image processing method according to  claim 11 ,
 wherein in the step of calculating the evaluation value, the processor calculates the evaluation value such that the evaluation value increases as an absolute value of the difference increases.   
     
     
         13 . A computer-readable recording medium, the recording medium having a program recorded thereon for causing a computer to execute each step of the image processing method according to  claim 12 . 
     
     
         14 . The image processing method according to  claim 11 ,
 wherein in the step of calculating the evaluation value, the processor calculates the evaluation value such that the evaluation value increases as a probability of the imaging location being outdoors increases.   
     
     
         15 . A computer-readable recording medium, the recording medium having a program recorded thereon for causing a computer to execute each step of the image processing method according to  claim 14 . 
     
     
         16 . The image processing method according to  claim 11 ,
 wherein in the step of calculating the evaluation value, the processor calculates the evaluation value such that the evaluation value decreases as the degree of blurring in the subject region increases.   
     
     
         17 . A computer-readable recording medium, the recording medium having a program recorded thereon for causing a computer to execute each step of the image processing method according to  claim 16 . 
     
     
         18 . A computer-readable recording medium, the recording medium having a program recorded thereon for causing a computer to execute each step of the image processing method according to  claim 11 .